Om Thakkar

Researcher, Google

Joined

December 2020

Names

Om Thakkar (Preferred)

Om Dipakbhai Thakkar

Emails

****@bu.edu (Confirmed)

****@google.com (Confirmed)

****@gmail.com (Confirmed)

****@psu.edu

Personal Links

Career & Education History

Researcher

Google (google.com)

2019 – Present

PhD student

Boston University (bu.edu)

2014 – 2019

Undergrad student

Dhirubhai Ambani Institute of Information and Communication Technology (daiict.ac.in)

2010 – 2014

Advisors, Relations & Conflicts

PhD Advisor

Dr. Adam Smith

2014 – 2019

Expertise

Privacy-preserving machine learning

2014 – Present

Publications

Why Is Public Pretraining Necessary for Private Model Training?
Arun Ganesh, Mahdi Haghifam, Milad Nasr, Sewoong Oh, Thomas Steinke, Om Thakkar, Abhradeep Guha Thakurta, Lun Wang
- ICML 2023 Poster
- Readers: Everyone
Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints
Virat Shejwalkar, Arun Ganesh, Rajiv Mathews, Om Thakkar, Abhradeep Guha Thakurta
- 23 Jan 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
Why Is Public Pretraining Necessary for Private Model Training?
Arun Ganesh, Mahdi Haghifam, Milad Nasr, Sewoong Oh, Thomas Steinke, Om Thakkar, Abhradeep Thakurta, Lun Wang
- 2023 (modified: 17 Apr 2023)
- CoRR 2023
- Readers: Everyone
Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints
Virat Shejwalkar, Arun Ganesh, Rajiv Mathews, Om Thakkar, Abhradeep Guha Thakurta
- Published: 01 Feb 2023, Last Modified: 14 Jan 2026
- Submitted to ICLR 2023
- Readers: Everyone
Measuring Forgetting of Memorized Training Examples
Matthew Jagielski, Om Thakkar, Florian Tramer, Daphne Ippolito, Katherine Lee, Nicholas Carlini, Eric Wallace, Shuang Song, Abhradeep Guha Thakurta, Nicolas Papernot, Chiyuan Zhang
- Published: 01 Feb 2023, Last Modified: 02 Mar 2023
- ICLR 2023 poster
- Readers: Everyone
Detecting Unintended Memorization in Language-Model-Fused ASR
W. Ronny Huang, Steve Chien, Om Dipakbhai Thakkar, Rajiv Mathews
- 2022 (modified: 03 Mar 2023)
- INTERSPEECH 2022
- Readers: Everyone
Extracting Targeted Training Data from ASR Models, and How to Mitigate It
Ehsan Amid, Om Dipakbhai Thakkar, Arun Narayanan, Rajiv Mathews, Françoise Beaufays
- 2022 (modified: 14 Apr 2023)
- INTERSPEECH 2022
- Readers: Everyone
Detecting Unintended Memorization in Language-Model-Fused ASR
W. Ronny Huang, Steve Chien, Om Thakkar, Rajiv Mathews
- 2022 (modified: 03 Mar 2023)
- CoRR 2022
- Readers: Everyone
Public Data-Assisted Mirror Descent for Private Model Training
Ehsan Amid, Arun Ganesh, Rajiv Mathews, Swaroop Ramaswamy, Shuang Song, Thomas Steinke, Vinith M. Suriyakumar, Om Thakkar, Abhradeep Thakurta
- 2022 (modified: 14 Apr 2023)
- ICML 2022
- Readers: Everyone
Extracting Targeted Training Data from ASR Models, and How to Mitigate It
Ehsan Amid, Om Thakkar, Arun Narayanan, Rajiv Mathews, Françoise Beaufays
- 2022 (modified: 14 Apr 2023)
- CoRR 2022
- Readers: Everyone

View all 41 publications

Co-Authors

View all 52 co-authors